DC Hub Intelligence

Report Finding

report_finding

File an observed anomaly on a DC Hub tool or endpoint as a brain finding so it is triaged like other detectors.

Instructions

PARTNER KEY ONLY: file what you observed on a DC Hub surface as a brain finding (detector external_audit) so it is triaged like every other detector's. class is one of completeness_contradiction, geography_leak, as_of_cite_as, pro_wall_dead_end, count_drift, stale_payload_complete, leak_past_pro_gate, link_hygiene, other; tool names the DC Hub tool or endpoint; quoted_fields carries the exact fields you saw (hashed for dedupe: the same observation re-filed within 24h bumps recurrence instead of inserting). Proxies POST /api/v1/inbox/findings with the session's own key; a key issued without a partner slug answers partner key required (403). 120 per key per day.

Input Schema

TableJSON Schema

Name	Required	Description
`args`	No	The arguments you called it with
`note`	No	One or two sentences of context
`tool`	Yes	The DC Hub tool or endpoint the finding is about, e.g. analyze_site
`class`	Yes	Finding class: completeness_contradiction (status full/partial_preview with empty withheld_fields), geography_leak (preview resolved outside the requested ISO/region), as_of_cite_as (as_of null while cite_as stamps a date), pro_wall_dead_end (a paid-plan wall that says stop while next_ask offers another paid-plan tool and no cheaper rung), count_drift (tool or asset counts disagree across doors), stale_payload_complete (a stale sub-feed inside a payload marked complete), leak_past_pro_gate (a paid-plan field served below its plan), link_hygiene (dead or wrong-shape links), other
`recurrence`	No	How many times you have seen it (default 1)
`session_id`	No	Your session identifier, if any
`observed_at`	No	ISO-8601 time you observed it
`quoted_fields`	No	The exact fields/values you observed (object, list or string); hashed for dedupe

Output Schema

TableJSON Schema

Name	Required	Description
`quota`	No	Caller quota state (remaining calls, tier).
`_entity`	No	Payload class (facility\|market\|iso_grid\|queue_results\|deal\|report\|response); branch on it.
`citation`	No	How to attribute DC Hub: {source, url, license, cite_as, retrieved_at}, or the attribution line as a string.
`provenance`	No	Source, method, as_of, verification_counts, license, cite_as; quote it when citing.
`_front_door`	No	First-tool hint: plan_query(intent) returns the ordered plan.
`_return_loop`	No	Next-session delta call (get_changes).
`site_evaluation_handoff`	No	Follow-up calls [{tool, parameters, why}] when the payload carries coordinates.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.12.43Oct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: discloses the dedupe mechanic (quoted_fields hashed; identical observation re-filed within 24h bumps recurrence instead of inserting), the proxy path and that the session's own key is used, the 403 behavior, and the 120/key/day rate limit. These are exactly the traits an agent cannot infer from destructiveHint=false and idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly 120 words with the partner-key gate front-loaded and no filler sentences. The semicolon-chained stream is dense and would scan better as discrete lines, but nothing is redundant and each clause carries new information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter write tool with an output schema, the description covers everything the caller must know: the access gate, the transport (POST /api/v1/inbox/findings), the failure response, the rate limit, and the dedupe consequence. Return-value shape is properly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the recorded baseline is 3, but the description contributes real semantics beyond it: quoted_fields is stated to be hashed for dedupe, and 'tool names the DC Hub tool or endpoint' clarifies the intended granularity. The enumeration of class values largely duplicates the schema's own enum descriptions, which caps this below a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: file an observation on a DC Hub surface as a brain finding under the external_audit detector. No sibling tool does anything comparable, and the 'so it is triaged like every other detector's' clause pins the downstream effect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear precondition (PARTNER KEY ONLY) and an explicit failure mode for the wrong key type ('a key issued without a partner slug answers partner key required (403)'), plus the daily quota that bounds usage. It stops short of stating when NOT to file (e.g. what belongs in 'other' vs. a more specific class), so it stops one notch short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server